Single-frame deep-learning super-resolution microscopy for intracellular dynamics imaging
Problem
Single-molecule localization microscopy needs thousands of frames, making imaging slow and phototoxic and blocking observation of fast intracellular dynamics.
Why it matters
Visualizing instantaneous live-cell processes at nanoscale requires fast, low-phototoxicity super-resolution imaging.
What the AI did
A deep-learning method (SFSRM) uses a subpixel edge map and multicomponent optimization to guide a neural network to reconstruct super-resolution images from a single diffraction-limited frame.
Results
Live-cell imaging with 30 nm spatial and 10 ms temporal resolution under tolerable signal density and signal-to-noise ratio.
Impact
Enables prolonged monitoring of subcellular dynamics at nanometer-millisecond scales.
Record
| Venue | Nature Communications |
|---|---|
| Published | 2023 |
| Work type | article |
| Authors | Rong Chen, Xiao Tang, Yuxuan Zhao, Zeyu Shen, Meng Zhang, Yusheng Shen, Tiantian Li, Casper Ho Yin Chung et al. |
| Citations | 117 (OpenAlex, at import time) |
| References | 73 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41467-023-38452-2 |
| Open access | gold |
| Keywords | deep learning, super-resolution microscopy, live-cell imaging, single-frame reconstruction |
Importance rating
real but narrower advance
Enables live-cell imaging at 30 nm and 10 ms, a genuinely new capability for observing fast subcellular dynamics; significant for cell biology, no scale stated.